FinalProject
2025-04-10
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
library(readr)
diabetes_dataset <- read_csv("diabetes_prediction_dataset.csv")## Rows: 100000 Columns: 9
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): gender, smoking_history
## dbl (7): age, hypertension, heart_disease, bmi, HbA1c_level, blood_glucose_l...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.#View(diabetes_dataset)Including Plots
You can also embed plots, for example:
diabetes_dataset## # A tibble: 100,000 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 80 0 1 never 25.2 6.6
## 2 Female 54 0 0 No Info 27.3 6.6
## 3 Male 28 0 0 never 27.3 5.7
## 4 Female 36 0 0 current 23.4 5
## 5 Male 76 1 1 current 20.1 4.8
## 6 Female 20 0 0 never 27.3 6.6
## 7 Female 44 0 0 never 19.3 6.5
## 8 Female 79 0 0 No Info 23.9 5.7
## 9 Male 42 0 0 never 33.6 4.8
## 10 Female 32 0 0 never 27.3 5
## # ℹ 99,990 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl># male datatset
male_data = diabetes_dataset %>% filter(gender == "Male")
# female dataset
female_data = diabetes_dataset %>% filter(gender == "Female")
female_data## # A tibble: 58,552 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 80 0 1 never 25.2 6.6
## 2 Female 54 0 0 No Info 27.3 6.6
## 3 Female 36 0 0 current 23.4 5
## 4 Female 20 0 0 never 27.3 6.6
## 5 Female 44 0 0 never 19.3 6.5
## 6 Female 79 0 0 No Info 23.9 5.7
## 7 Female 32 0 0 never 27.3 5
## 8 Female 53 0 0 never 27.3 6.1
## 9 Female 54 0 0 former 54.7 6
## 10 Female 78 0 0 former 36.0 5
## # ℹ 58,542 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl># males and females within original dataset that have a "normal" A1C
female_data %>% filter(HbA1c_level <= 5.7) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 27397male_data %>% filter(HbA1c_level <= 5.7) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 18865# count of people (male and female) with both heart disease and diabetes
diabetes_dataset %>% filter(diabetes == 1, heart_disease == 1)## # A tibble: 1,267 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Male 67 0 1 not current 27.3 6.5
## 2 Male 57 1 1 not current 27.8 6.6
## 3 Male 80 0 1 former 24.4 7.5
## 4 Male 75 0 1 not current 28.1 7.5
## 5 Male 69 0 1 former 24.1 6.8
## 6 Female 59 0 1 never 60.3 8.8
## 7 Male 80 0 1 former 33.0 6
## 8 Female 62 1 1 former 44.2 8.2
## 9 Female 62 1 1 never 43.2 8.8
## 10 Female 76 0 1 former 25.7 9
## # ℹ 1,257 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>diabetes_dataset %>% filter(diabetes == 1, heart_disease == 1) %>% tally() # this is saying how many rows are in the data group and tally ***## # A tibble: 1 × 1
## n
## <int>
## 1 1267# count of overweight people based on bmi who have heart disease
diabetes_dataset %>% group_by(bmi >= 30) %>% filter(heart_disease == 1)## # A tibble: 3,942 × 10
## # Groups: bmi >= 30 [2]
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 80 0 1 never 25.2 6.6
## 2 Male 76 1 1 current 20.1 4.8
## 3 Female 72 0 1 former 27.9 6.5
## 4 Male 67 0 1 not current 27.3 6.5
## 5 Female 77 1 1 never 32.0 5
## 6 Female 59 0 1 ever 23.1 6.5
## 7 Male 68 1 1 current 27.3 5
## 8 Male 59 0 1 ever 30.8 5
## 9 Female 80 0 1 never 29.6 5.8
## 10 Male 57 1 1 not current 27.8 6.6
## # ℹ 3,932 more rows
## # ℹ 3 more variables: blood_glucose_level <dbl>, diabetes <dbl>,
## # `bmi >= 30` <lgl>diabetes_dataset %>% group_by(bmi >= 30) %>% filter(heart_disease == 1) ## # A tibble: 3,942 × 10
## # Groups: bmi >= 30 [2]
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 80 0 1 never 25.2 6.6
## 2 Male 76 1 1 current 20.1 4.8
## 3 Female 72 0 1 former 27.9 6.5
## 4 Male 67 0 1 not current 27.3 6.5
## 5 Female 77 1 1 never 32.0 5
## 6 Female 59 0 1 ever 23.1 6.5
## 7 Male 68 1 1 current 27.3 5
## 8 Male 59 0 1 ever 30.8 5
## 9 Female 80 0 1 never 29.6 5.8
## 10 Male 57 1 1 not current 27.8 6.6
## # ℹ 3,932 more rows
## # ℹ 3 more variables: blood_glucose_level <dbl>, diabetes <dbl>,
## # `bmi >= 30` <lgl># "obese men" with bmi higher than 30 and that have diabetes (tally on second line)
male_data %>% filter(bmi >= 30, diabetes == 1)## # A tibble: 1,903 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Male 50 0 0 former 37.2 9
## 2 Male 53 0 0 current 30.8 6.6
## 3 Male 76 0 0 never 31.9 7.5
## 4 Male 63 1 0 ever 35.1 5.8
## 5 Male 48 1 0 current 36.1 6.8
## 6 Male 37 0 0 never 37.2 7
## 7 Male 36 0 0 not current 46.1 6.2
## 8 Male 50 0 0 never 31.8 7.5
## 9 Male 43 0 0 never 69.4 7.5
## 10 Male 43 1 0 not current 40.9 6.6
## # ℹ 1,893 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>male_data %>% filter(bmi >= 30, diabetes == 1) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 1903# "obese women" with bmi higher than 30 and that have diabetes (tally on second line)
female_data %>% filter(bmi >= 30, diabetes == 1)## # A tibble: 2,330 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 67 0 0 never 63.5 8.8
## 2 Female 36 0 0 current 32.3 6.2
## 3 Female 77 0 0 never 31.7 6.5
## 4 Female 47 0 0 never 36.5 7.5
## 5 Female 61 0 0 not current 39.4 9
## 6 Female 80 0 0 former 36.2 6.5
## 7 Female 52 1 0 never 50.3 6.6
## 8 Female 68 0 0 No Info 40.3 7.5
## 9 Female 70 0 0 not current 33.2 7.5
## 10 Female 67 0 0 former 32.3 7
## # ℹ 2,320 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>female_data %>% filter(bmi >= 30, diabetes == 1) %>% tally() # grouped by gender ***## # A tibble: 1 × 1
## n
## <int>
## 1 2330# "underweight men" with bmi lower than 19 and that have diabetes (tally on second line)
male_data %>% filter(bmi <= 19, diabetes == 1)## # A tibble: 21 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Male 42 0 0 current 11.9 6
## 2 Male 6 0 0 never 15.7 6.1
## 3 Male 71 1 0 former 13.2 6.6
## 4 Male 14 0 0 never 19.0 6.6
## 5 Male 54 0 0 never 18.9 6
## 6 Male 61 1 0 never 18.4 6.5
## 7 Male 4 0 0 never 18.7 6
## 8 Male 51 0 0 current 17.8 6.2
## 9 Male 80 1 0 current 19.0 6.6
## 10 Male 6 0 0 No Info 15.6 9
## # ℹ 11 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>male_data %>% filter(bmi <= 19, diabetes == 1) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 21# "underweight women" with bmi lower than 19 and that have diabetes (tally on second line)
female_data %>% filter(bmi <= 19, diabetes == 1)## # A tibble: 57 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 79 0 0 not current 18.1 7
## 2 Female 4 0 0 No Info 15.0 6.5
## 3 Female 51 0 0 current 17.4 7
## 4 Female 9 0 0 never 16 6.1
## 5 Female 60 0 0 No Info 17.9 8.2
## 6 Female 13 0 0 No Info 17.3 6.2
## 7 Female 80 0 0 never 17.4 6.5
## 8 Female 8 0 0 No Info 14.3 7.5
## 9 Female 80 0 0 never 17.8 6.2
## 10 Female 78 1 0 not current 17.7 8.8
## # ℹ 47 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>female_data %>% filter(bmi <= 19, diabetes == 1) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 57# the assumption is that overweight people are more likely to have diabetes. Below is the code and tally of MEN who are overweight in terms of bmi and DONT have diabetes
male_data %>% filter(bmi >= 30, diabetes == 0)## # A tibble: 7,445 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Male 42 0 0 never 33.6 4.8
## 2 Male 15 0 0 never 30.4 6.1
## 3 Male 40 0 0 current 36.4 6
## 4 Male 30 0 0 never 33.8 6.1
## 5 Male 34 0 0 never 31.2 5.8
## 6 Male 54 0 0 never 31.9 6.6
## 7 Male 79 0 0 former 31.2 5.8
## 8 Male 54 0 0 former 32.8 5
## 9 Male 38 0 0 never 55.6 6.5
## 10 Male 58 0 0 former 36.5 5.8
## # ℹ 7,435 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>male_data %>% filter(bmi >= 30, diabetes == 0) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 7445# the assumption is that overweight people are more likely to have diabetes. Below is the code and tally of WOMEN who are overweight in terms of bmi and DONT have diabetes
female_data %>% filter(bmi >= 30, diabetes == 0)## # A tibble: 11,852 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 54 0 0 former 54.7 6
## 2 Female 78 0 0 former 36.0 5
## 3 Female 53 0 0 No Info 31.8 4
## 4 Female 34 0 0 never 56.4 6.2
## 5 Female 77 1 1 never 32.0 5
## 6 Female 27 0 0 not current 30.2 5.7
## 7 Female 37 0 0 No Info 30.5 5.7
## 8 Female 56 0 0 never 31.0 6.5
## 9 Female 44 0 0 never 37.4 5.7
## 10 Female 30 0 0 No Info 50.1 6
## # ℹ 11,842 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>female_data %>% filter(bmi >= 30, diabetes == 0) %>% tally()## # A tibble: 1 × 1
## n
## <int>
## 1 11852Diabetes Dataset
| gender | age | hypertension | heart_disease | smoking_history | bmi | HbA1c_level | blood_glucose_level | diabetes |
|---|---|---|---|---|---|---|---|---|
| Female | 80 | 0 | 1 | never | 25.19 | 6.6 | 140 | 0 |
| Female | 54 | 0 | 0 | No Info | 27.32 | 6.6 | 80 | 0 |
| Male | 28 | 0 | 0 | never | 27.32 | 5.7 | 158 | 0 |
| Female | 36 | 0 | 0 | current | 23.45 | 5.0 | 155 | 0 |
| Male | 76 | 1 | 1 | current | 20.14 | 4.8 | 155 | 0 |
| Female | 20 | 0 | 0 | never | 27.32 | 6.6 | 85 | 0 |
diabetes_dataset## # A tibble: 100,000 × 9
## gender age hypertension heart_disease smoking_history bmi HbA1c_level
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Female 80 0 1 never 25.2 6.6
## 2 Female 54 0 0 No Info 27.3 6.6
## 3 Male 28 0 0 never 27.3 5.7
## 4 Female 36 0 0 current 23.4 5
## 5 Male 76 1 1 current 20.1 4.8
## 6 Female 20 0 0 never 27.3 6.6
## 7 Female 44 0 0 never 19.3 6.5
## 8 Female 79 0 0 No Info 23.9 5.7
## 9 Male 42 0 0 never 33.6 4.8
## 10 Female 32 0 0 never 27.3 5
## # ℹ 99,990 more rows
## # ℹ 2 more variables: blood_glucose_level <dbl>, diabetes <dbl>Male vs. Female Blood Sugar Levels (HbA1c)
| gender | age | hypertension | heart_disease | smoking_history | bmi | HbA1c_level | blood_glucose_level | diabetes | HbA1c_category |
|---|---|---|---|---|---|---|---|---|---|
| Female | 80 | 0 | 1 | never | 25.19 | 6.6 | 140 | 0 | Diabetes ≥ 6.5% |
| Female | 54 | 0 | 0 | No Info | 27.32 | 6.6 | 80 | 0 | Diabetes ≥ 6.5% |
| Male | 28 | 0 | 0 | never | 27.32 | 5.7 | 158 | 0 | Prediabetes 5.7% - 6.4% |
| Female | 36 | 0 | 0 | current | 23.45 | 5.0 | 155 | 0 | Normal < 5.7% |
| Male | 76 | 1 | 1 | current | 20.14 | 4.8 | 155 | 0 | Normal < 5.7% |
| Female | 20 | 0 | 0 | never | 27.32 | 6.6 | 85 | 0 | Diabetes ≥ 6.5% |
Similar Prevalence of Prediabetes – The proportion of individuals categorized as having prediabetes (HbA1c 5.7% - 6.4%) is almost identical between males (41.3%) and females (41.4%). This suggests that prediabetes affects both genders at nearly the same rate.
- Slightly Higher Diabetes Rates Among Males – More males (21.6%) fall into the diabetes (HbA1c ≥ 6.5%) category compared to females (20.2%). While the difference is small, it might indicate that men have a slightly higher risk of diabetes in this dataset.
Females Have a Slightly Higher Proportion of Normal Blood Sugar Levels – More females (38.4%) fall into the normal blood sugar category (<5.7%) compared to males (37.1%). This may indicate some slight protective factors or lifestyle differences in this group.
Since more males are in the diabetes category, there could be gender-related risk factors worth exploring—such as diet, activity levels, or genetic predisposition.
Overall, blood sugar regulation patterns appear fairly balanced between genders, but small differences suggest potential areas for further investigation.
Similar Prevalence of Prediabetes
The proportion of individuals classified as having prediabetes (HbA1c
5.7% - 6.4%) is nearly identical between males (41.3%)
and females (41.4%). This suggests no significant
disparity.
BMI Distribution by Hypertension Status Plot
Shows the distribution of BMI values based on hypertension status. A violin plot is great for visualizing the distribution and density of BMI across hypertension categories,
Shape and width: The width of each “violin” represents the density of BMI values at different levels. Wider sections mean more individuals have that BMI, while narrower sections indicate fewer people at those values.
Comparison of distributions: The blue violin represents people without hypertension (hypertension = 0), while the red violin represents those with hypertension (hypertension = 1). By comparing them, you can see how BMI differs between these groups.
The horizontal line around 25 BMI: This marks the median BMI for each group. Since both violins have a horizontal line in roughly the same position, it suggests that the median BMI is around 25 for both hypertensive and non-hypertensive individuals.
Density trends: If the violins have different thicknesses in certain BMI ranges, it tells you which BMI values are more or less common in each group. People with hypertension seem to have a higher BMI overall, but both groups share a similar median.
The distribution shape is different—for example, if one violin is wider at higher BMI values, it suggests that hypertension is more common among individuals with higher BMI.
Outliers or extreme values might appear as small bulges or extended tails at the ends of the violins, showing individuals with very high or low BMI.
Smokers go brrr
In the smoking data there are 6 unique values
- Never: Has Never smoked
- Not current: Has smoked but is not currently smoking
- Former: Has quit smoking (abstained for longer than)
- Current: Is currently a smoker
- Ever: Has ever smoked regardless of current smoking status
- No Info: No smoking history information available
The total amount of people who fall into each category is as follows;
- Never: 35095
- Not current: 6447
- Former: 9352
- Current: 9286
- Ever: 4004
- No Info: 35816
There is quite a sizable amount of people in the No info category.
The total number of people in the dataset is 100000. To help clean up the data, we can filter ‘No Info’ people out. When we do that we get 64184.
# Figure out the unique categories of smoking history
unique(diabetes_dataset$smoking_history)## [1] "never" "No Info" "current" "former" "ever"
## [6] "not current"# Count amount of people who belong to each unique category
diabetes_dataset %>% group_by(smoking_history) %>% summarise(total_people = n())## # A tibble: 6 × 2
## smoking_history total_people
## <chr> <int>
## 1 No Info 35816
## 2 current 9286
## 3 ever 4004
## 4 former 9352
## 5 never 35095
## 6 not current 6447smoking_diabetes_dataset <- diabetes_dataset %>%
filter(smoking_history != 'No Info') %>%
group_by(smoking_history, diabetes) %>%
summarise(total = n())## `summarise()` has grouped output by 'smoking_history'. You can override using
## the `.groups` argument.Now we can graph the relationship between
library(dplyr)
library(ggplot2)
# Data prep
bmi_heart_gender <- diabetes_dataset %>%
filter(heart_disease == 1) %>%
mutate(
bmi_category = case_when(
bmi <= 19 ~ "Underweight",
bmi >= 30 ~ "Overweight",
TRUE ~ NA_character_
)
) %>%
filter(!is.na(bmi_category)) %>%
group_by(gender, bmi_category) %>%
summarise(count = n(), .groups = 'drop') %>%
group_by(gender) %>%
mutate(percentage = round(100 * count / sum(count), 1))
# Make sure the bmi_category is an ordered factor so the line connects correctly
bmi_heart_gender$bmi_category <- factor(bmi_heart_gender$bmi_category,
levels = c("Underweight", "Overweight"))
# Dot + Line plot
ggplot(bmi_heart_gender, aes(x = bmi_category, y = count, group = gender, color = gender)) +
geom_line(aes(group = gender), position = position_dodge(width = 0.5), linewidth = 1) +
geom_point(size = 5, position = position_dodge(width = 0.5)) +
geom_text(aes(label = paste0(count, " (", percentage, "%)")),
vjust = -1,
position = position_dodge(width = 0.5)) +
labs(
title = "Heart Disease Cases by Gender and BMI Category (Dot-Line Plot)",
x = "BMI Category",
y = "Count of People with Heart Disease",
color = "Gender"
) +
theme_minimal()
library(dplyr)
library(ggplot2)
# Prepare the data
bmi_heart_gender <- diabetes_dataset %>%
filter(heart_disease == 1) %>%
mutate(
bmi_category = case_when(
bmi <= 19 ~ "Underweight",
bmi >= 30 ~ "Overweight",
TRUE ~ NA_character_
)
) %>%
filter(!is.na(bmi_category)) %>%
group_by(gender, bmi_category) %>%
summarise(count = n(), .groups = 'drop') %>%
group_by(gender) %>%
mutate(percentage = round(100 * count / sum(count), 1))
# Plot
ggplot(bmi_heart_gender, aes(x = bmi_category, y = count, fill = gender)) +
geom_bar(stat = "identity", position = position_dodge(width = 0.7)) +
geom_text(aes(label = paste0(count, " (", percentage, "%)")),
vjust = -0.5,
position = position_dodge(width = 0.7)) +
labs(
title = "Count and Percentage of Heart Disease Cases by Gender and BMI Category",
x = "BMI Category",
y = "Count of People with Heart Disease",
fill = "Gender"
) +
theme_minimal()
# load needed packages
library(dplyr)
library(ggplot2)
# 1. Summarise men
men_summary <- male_data %>%
summarise(
count = sum(bmi >= 30 & diabetes == 0),
total = n()
) %>%
mutate(
sex = "Men",
percent = count / total * 100
)
# 2. Summarise women
women_summary <- female_data %>%
summarise(
count = sum(bmi >= 30 & diabetes == 0),
total = n()
) %>%
mutate(
sex = "Women",
percent = count / total * 100
)
# 3. Combine into one data frame
summary_df <- bind_rows(men_summary, women_summary)
# 4. Plot
ggplot(summary_df, aes(x = sex, y = count, fill = sex)) +
geom_col(width = 0.6) +
geom_text(aes(label = sprintf("%d (%.1f%%)", count, percent)),
vjust = -0.5, size = 4) +
scale_y_continuous(expand = expansion(mult = c(0, 0.1))) +
labs(
title = "Count of Overweight (BMI ≥ 30) without diabetes, by Sex",
x = NULL,
y = "Number of Individuals",
fill = NULL
) +
theme_minimal(base_size = 14) +
theme(legend.position = "none")